Skip to content

@ModelTC ModelTC

Change the repository type filter

All

    Repositories list

    72 repositories

    • mtc-token-healing

      Public
      Token healing implementation in Rust
      Rust
      •
      Apache License 2.0
      •0•4•0•1•Updated Feb 23, 2026Feb 23, 2026

    • MoDES

      Public
      [CVPR 2026] This is the official PyTorch implementation of "MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping"…
      moecvprvlmmultimodalmixture-of-expertskimi-vlqwen3-vlcvpr-2026
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Feb 21, 2026Feb 21, 2026

    • general-sam-py

      Public
      Python bindings for general-sam and some utilities
      Python
      •
      Apache License 2.0
      •0•5•0•0•Updated Feb 20, 2026Feb 20, 2026

    • LightTTS

      Public
      LightTTS is a lightweight TTS inference framework optimized for CosyVoice2 and CosyVoice3, enabling fast and scalable speech synthesis in Python and supports st…
      text-to-speechreal-timettsspeech-synthesislow-latencytensorrtinference-optimizationaudio-generationcosyvoicecosyvoice2
      Python
      •
      Apache License 2.0
      •7•28•2•0•Updated Feb 20, 2026Feb 20, 2026

    • LightLLM

      Public
      LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed perf…
      nlpdeep-learningllamagptmodel-servingllmopenai-triton
      Python
      •
      Apache License 2.0
      •300•3.9k•82•35•Updated Feb 20, 2026Feb 20, 2026

    • Qwen-Image-Edit-Causal

      Public
      In our implementation of Qwen-Image-Edit, we employ block causal attention to improve inference speed.
      Python
      •
      Apache License 2.0
      •2•31•1•0•Updated Feb 16, 2026Feb 16, 2026

    • LightMem

      Public
      Python
      •
      Apache License 2.0
      •0•4•0•0•Updated Feb 14, 2026Feb 14, 2026

    • GenRL

      Public
      Reinforcement Learning Framework for Visual Generation
      reinforcement-learninginfrarlwandpoimagegenerationvideogenerationgrpowan-videowan21
      Python
      •
      Apache License 2.0
      •1•43•0•0•Updated Feb 13, 2026Feb 13, 2026

    • QVGen

      Public
      [ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".
      waniclrqatvideo-generationdiffusion-modelsvideogenmodel-quantizationquantization-aware-traininggenerative-aitext-to-video-generation
      Python
      •
      Apache License 2.0
      •0•13•0•0•Updated Feb 11, 2026Feb 11, 2026

    • SageAttention3-sparse

      Public
      [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across la…
      Cuda
      •
      Apache License 2.0
      •355•1•0•0•Updated Feb 11, 2026Feb 11, 2026

    • LightX2V

      Public
      Light Image Video Generation Inference Framework
      video-generationdiffusion-modelswan-videoauto-regressive-diffusion-model
      Python
      •
      Apache License 2.0
      •163•2k•131•2•Updated Feb 11, 2026Feb 11, 2026

    • VideoAlign

      Public
      Python
      •
      MIT License
      •0•1•0•0•Updated Feb 10, 2026Feb 10, 2026

    • HPSv3

      Public
      Python
      •
      MIT License
      •0•1•0•0•Updated Feb 10, 2026Feb 10, 2026

    • SageAttention

      Public
      Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and v…
      Cuda
      •
      Apache License 2.0
      •355•3•0•1•Updated Feb 10, 2026Feb 10, 2026

    • general-sam

      Public
      A general suffix automaton implementation in Rust with Python bindings
      Rust
      •
      Apache License 2.0
      •0•9•0•1•Updated Feb 9, 2026Feb 9, 2026

    • LightKernel

      Public
      HTML
      •
      Apache License 2.0
      •0•3•0•0•Updated Feb 4, 2026Feb 4, 2026

    • Prototype

      Public
      Python
      •
      Apache License 2.0
      •3•14•0•0•Updated Feb 3, 2026Feb 3, 2026

    • ComfyUI-Lightx2vWrapper

      Public
      ComfyUI custom node for lightx2v
      comfyuicomfyui-nodes
      Python
      •
      MIT License
      •7•79•4•0•Updated Feb 3, 2026Feb 3, 2026

    • lightx2v_examples

      Public
      0•0•0•0•Updated Jan 23, 2026Jan 23, 2026

    • modeltc.github.io

      Public
      HTML
      •0•0•0•0•Updated Jan 14, 2026Jan 14, 2026

    • SpargeAttn

      Public
      [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
      Cuda
      •
      Apache License 2.0
      •86•0•0•0•Updated Jan 12, 2026Jan 12, 2026

    • Qwen-Image-Lightning

      Public
      Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
      Python
      •
      Apache License 2.0
      •44•1.2k•29•0•Updated Jan 1, 2026Jan 1, 2026

    • verl

      Public
      verl: Volcano Engine Reinforcement Learning for LLMs
      Python
      •
      Apache License 2.0
      •3.3k•1•0•0•Updated Dec 15, 2025Dec 15, 2025

    • slime

      Public
      slime is an LLM post-training framework for RL Scaling.
      Python
      •
      Apache License 2.0
      •566•0•0•0•Updated Dec 8, 2025Dec 8, 2025

    • lightllm-blog

      Public
      SCSS
      •
      MIT License
      •1•1•0•1•Updated Nov 26, 2025Nov 26, 2025

    • greedy-tokenizer

      Public
      Greedily tokenize strings with the longest tokens iteratively.
      Python
      •
      Apache License 2.0
      •0•0•0•3•Updated Nov 24, 2025Nov 24, 2025

    • LightCompress

      Public
      [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
      benchmarkdeploymenttoolevaluationpruningquantizationwanawqlarge-language-modelsllm
      Python
      •
      Apache License 2.0
      •70•681•40•0•Updated Nov 19, 2025Nov 19, 2025

    • Wan2.2-Lightning

      Public
      Wan2.2-Lightning: Speed up wan2.2 model with distillation
      Python
      •
      Apache License 2.0
      •1.7k•270•21•0•Updated Nov 7, 2025Nov 7, 2025

    • LTX-Video-Q8-Kernels

      Public
      Python
      •17•0•0•0•Updated Nov 6, 2025Nov 6, 2025

    • SageAttention-1104

      Public
      [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across la…
      Cuda
      •
      Apache License 2.0
      •355•0•0•0•Updated Nov 6, 2025Nov 6, 2025